Gen AI Engineer - RAG Systems & AI Transformation

Summary

GenAI Engineer

advanced Retrieval-Augmented Generation (RAG) systems

Your role in our mission

• Architect and implement

  scalable RAG systems using Python and modern GenAI tools.
• Build

  custom pipelines

  for document ingestion, chunking strategies, and embedding generation. Working knowledge in

  LlamaIndex

  is preferable.
• Have a deep knowledge in using AI augmented tools like GitHub Copilot. Experience in developing custom extensions
• Evaluate and implement different

  embedding models

  (OpenAI, Azure OpenAI, Cohere, etc.) and

  chunking strategies

  (fixed-size, semantic-aware, overlap-based).
• Create and optimize

  indexing strategies

  (vector, hybrid, keyword-based, hierarchical) for performance and accuracy.
• Work with

  Azure AI Services

  , particularly Azure Cognitive Search and OpenAI integration, to deploy end-to-end AI applications.
• Collaborate closely with cross-functional teams including data engineers, product managers, and domain experts.
• Conduct

  AI enablement sessions

  , workshops, and hands-on labs to upskill internal teams on GenAI usage and best practices.
• Participate in code reviews, contribute to best practices, and ensure the reliability, scalability, and maintainability of AI systems.

What we're looking for

• 5+ years of experience

  in software engineering, with strong expertise in

  Python

  .

• 2 years of

  proven track record of building and deploying

  RAG-based GenAI solutions

  .
• Hands-on experience with

  LlamaIndex

  ,

  LangChain

  , or equivalent frameworks.
• Familiarity with prompt engineering, prompt tuning, and managing

  custom Copilot extensions

  .
• Strong understanding of

  LLMs

  , vector databases (like FAISS, Pinecone, Azure Cognitive Search), and

  embedding techniques

  .
• Solid knowledge of

  Azure AI

  , cloud deployment, and enterprise integration strategies.
• Proficiency with version control and collaborative development using

  GitHub

  .

What you should expect in this role

• Architect and implement

  scalable RAG systems using Python and modern GenAI tools.
• Build

  custom pipelines

  for document ingestion, chunking strategies, and embedding generation. Working knowledge in

  LlamaIndex

  is preferable.
• Have a deep knowledge in using AI augmented tools like GitHub Copilot. Experience in developing custom extensions
• Evaluate and implement different

  embedding models

  (OpenAI, Azure OpenAI, Cohere, etc.) and

  chunking strategies

  (fixed-size, semantic-aware, overlap-based).
• Create and optimize

  indexing strategies

  (vector, hybrid, keyword-based, hierarchical) for performance and accuracy.
• Work with

  Azure AI Services

  , particularly Azure Cognitive Search and OpenAI integration, to deploy end-to-end AI applications.
• Collaborate closely with cross-functional teams including data engineers, product managers, and domain experts.
• Conduct

  AI enablement sessions

  , workshops, and hands-on labs to upskill internal teams on GenAI usage and best practices.
• Participate in code reviews, contribute to best practices, and ensure the reliability, scalability, and maintainability of AI systems.